通信与信息技术Issue(2)：32-35,41,5.
一种轻量化三维人体姿态估计算法
A lightweight 3D human pose estimation algorithm
汪洋继鸿 1张路 1于越 2王健1
作者信息
- 1. 大连民族大学机电工程学院,辽宁大连 116605
- 2. 北方民族大学电气信息工程学院,宁夏银川 750021
- 折叠
摘要
Abstract
Aiming at the practical application requirements of 3D human pose estimation,a lightweight 3D human pose estimation model dilated sparse attention network based on dilated convolutional ResNet module and sparse attention is proposed.Firstly,the Monocular,One-stage,Regression of multiple 3D people network is used as the basic pose estimation model,and the convolution of the basic ResNet module in the branch is replaced by the dilated convolution.In order to reduce the number of model parameters without reducing the accuracy;Secondly,Sparse Attention is embedded in the branch to strengthen the context understanding ability to im-prove the accuracy.Finally,after 7 datasets training and 3DPW dataset testing,the feasibility of the model is verified.The experimental results show that the total number of DS-Net parameters is reduced by 53.8%.Compared with ROMP,MPJPE and PA-MPJPE reduce 1.8%and 2.9%respectively in 3D human pose estimation tasks,which can meet the requirements of practical application scenarios.关键词
姿态估计/空洞卷积/Sparse Attention/轻量化Key words
Pose estimation/Dilated convolution/Sparse attention/Lightweight分类
信息技术与安全科学引用本文复制引用
汪洋继鸿,张路,于越,王健..一种轻量化三维人体姿态估计算法[J].通信与信息技术,2024,(2):32-35,41,5.
